ArticleChemical science2025
Assessment of fine-tuned large language models for real-world chemistry and material science applications.
Abstract read
In one paragraph
Article in Chemical science, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 17 papers.
0numbers the graph read from it
0cells of the map it votes in
17citing papers in PubMed
–field-weighted citation impact
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
17 citing papers in PubMed.
- Automating Chemical Reasoning in High-Throughput Phase Identification With a Probabilistic, LLM-Guided Framework.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Porous Organic Polymers: From Molecular Design to Scalable Technologies.Small (Weinheim an der Bergstrasse, Germany) · 2026Review
- BB-EIT: A Generalized Prediction Model for Protein Adsorption on Polymer Brushes Using Augmented Chemical Embeddings.ACS applied materials & interfaces · 2026Article
- Sustainable Materials Design With Multi-Modal Artificial Intelligence.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Review
- Can You Help ChatGPT Get an "A" in Organic Chemistry? Teaching Effective Prompting of Large Language Models for Reaction Prediction.Journal of chemical education · 2026Article
- A survey on large language models in biology and chemistry.Experimental & molecular medicine · 2026Review
- Boosting Computational Catalysis and Chemical Reactivity with Artificial Intelligence.Journal of the American Chemical Society · 2026Review
- General-Purpose Models for the Chemical Sciences: LLMs and Beyond.Chemical reviews · 2026Review
- Application and Prospects of Large Language Models in Small-Molecule Drug Discovery.Analytical chemistry · 2025Review
- Cartesian equivariant representations for learning and understanding molecular orbitals.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Experimental Validation of Modeling Approaches Describing the Crystallization of Pure Triacylglycerides and Their Mixtures: A Review.Comprehensive reviews in food science and food safety · 2025Review
- Artificial Intelligence Paradigms for Next-Generation Metal-Organic Framework Research.Journal of the American Chemical Society · 2025Review
- Exploring the chemical design space of metal-organic frameworks for photocatalysis.Chemical science · 2025Article
- Explainable Synthesizability Prediction of Inorganic Crystal Polymorphs Using Large Language Models.Angewandte Chemie (International ed. in English) · 2025Article
- A Perspective on Foundation Models in Chemistry.JACS Au · 2025Review
- Neural networks and foundation models: two strategies for EEG-to-fMRI prediction.Frontiers in systems biology · 2025Article
- Advancing plant metabolic research by using large language models to expand databases and extract labeled data.Applications in plant sciencesArticle
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
50 authors.
Joren Van HerckLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0009-0005-5108-5061
María Victoria GilLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0000-0002-2258-3011
Kevin Maik JablonkaLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0000-0003-4894-4660
Alex AbrudanYusuf Hamied Department of Chemistry, University of Cambridge Cambridge CB2 1EW UK.ORCID https://orcid.org/0009-0003-7142-4425
Andy S AnkerDepartment of Energy Conversion and Storage, Technical University of Denmark DK-2800 Kgs. Lyngby Denmark.ORCID https://orcid.org/0000-0002-7403-6642
Mehrdad AsgariDepartment of Chemical Engineering & Biotechnology, University of Cambridge Philippa Fawcett Drive Cambridge CB3 0AS UK.ORCID https://orcid.org/0000-0002-5427-1610
Ben BlaiszikDepartment of Computer Science, University of Chicago Chicago IL 60637 USA.ORCID https://orcid.org/0000-0002-5326-4902
Antonio BuffoDepartment of Applied Science and Technology (DISAT), Politecnico di Torino 10129 Turino Italy.ORCID https://orcid.org/0000-0002-4152-0593
Leander ChoudhuryLaboratory of Catalysis and Organic Synthesis (LCSO), Institute of Chemical Sciences and Engineering (ISIC), École Polytechnique Fédérale de Lausanne (EPFL) CH-1015 Lausanne Switzerland.ORCID https://orcid.org/0009-0000-3226-3639
Clemence CorminboeufLaboratory for Computational Molecular Design (LCMD), Institute of Chemical Sciences and Engineering (ISIC), École Polytechnique Fédérale de Lausanne (EPFL) CH-1015 Lausanne Switzerland.ORCID https://orcid.org/0000-0001-7993-2879
Hilal DaglarDepartment of Chemical and Biological Engineering, Koç University Rumelifeneri Yolu, Sariyer 34450 Istanbul Turkey.ORCID https://orcid.org/0000-0002-5820-2452
Amir Mohammad ElahiLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0009-0001-5907-101X
Ian T FosterDepartment of Computer Science, University of Chicago Chicago IL 60637 USA.ORCID https://orcid.org/0000-0003-2129-5269
Susana GarciaThe Research Centre for Carbon Solutions (RCCS), School of Engineering and Physical Sciences, Heriot-Watt University Edinburgh EH14 4AS UK.ORCID https://orcid.org/0000-0002-3713-311X
Matthew GarvinThe Research Centre for Carbon Solutions (RCCS), School of Engineering and Physical Sciences, Heriot-Watt University Edinburgh EH14 4AS UK.ORCID https://orcid.org/0000-0002-6605-6002
Guillaume GodinBIGCHEM GmbH Valerystraße 49 85716 Unterschleißheim Germany.ORCID https://orcid.org/0000-0001-9828-386X
Lydia L GoodYusuf Hamied Department of Chemistry, University of Cambridge Cambridge CB2 1EW UK.ORCID https://orcid.org/0000-0001-5308-8542
Jianan GuInstitute of Metallic Biomaterials, Helmholtz Zentrum Hereon Geesthacht Germany.ORCID https://orcid.org/0009-0003-0422-5610
Noémie Xiao HuLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0009-0000-9301-4505
Xin JinLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0000-0002-2618-9775
Tanja JunkersPolymer Reaction Design Group, School of Chemistry, Monash University Clayton VIC 3800 Australia.ORCID https://orcid.org/0000-0002-6825-5777
Seda KeskinDepartment of Chemical and Biological Engineering, Koç University Rumelifeneri Yolu, Sariyer 34450 Istanbul Turkey.ORCID https://orcid.org/0000-0001-5968-0336
Tuomas P J KnowlesYusuf Hamied Department of Chemistry, University of Cambridge Cambridge CB2 1EW UK.ORCID https://orcid.org/0000-0002-7879-0140
Ruben LaplazaLaboratory for Computational Molecular Design (LCMD), Institute of Chemical Sciences and Engineering (ISIC), École Polytechnique Fédérale de Lausanne (EPFL) CH-1015 Lausanne Switzerland.ORCID https://orcid.org/0000-0001-6315-4398
Michele LessonaDepartment of Applied Science and Technology (DISAT), Politecnico di Torino 10129 Turino Italy.ORCID https://orcid.org/0009-0003-1486-7705
Sauradeep MajumdarLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0000-0002-2095-3082
Hossein MashhadimoslemDepartment of Chemical Engineering, University of Waterloo Waterloo N2L3G1 Canada.ORCID https://orcid.org/0000-0001-9104-8138
Ruaraidh D McIntoshInstitute of Chemical Sciences, School of Engineering and Physical Sciences, Heriot-Watt University Edinburgh EH14 4AS UK.ORCID https://orcid.org/0000-0002-7563-5655
Seyed Mohamad MoosaviChemical Engineering & Applied Chemistry, University of Toronto Toronto Ontario M5S 3E5 Canada.ORCID https://orcid.org/0000-0002-0357-5729
Beatriz MouriñoLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0000-0003-1670-3985
Francesca NerliDipartimento di Chimica e Chimica Industriale, Unità di Ricerca INSTM, Università di Pisa Via Giuseppe Moruzzi 13 56124 Pisa Italy.ORCID https://orcid.org/0009-0008-5932-4583
Covadonga PevidaInstituto de Ciencia y TecnologÍa del Carbono (INCAR), CSIC Francisco Pintado Fe 26 33011 Oviedo Spain.ORCID https://orcid.org/0000-0002-4662-8448
Neda PoudinehThe Research Centre for Carbon Solutions (RCCS), School of Engineering and Physical Sciences, Heriot-Watt University Edinburgh EH14 4AS UK.ORCID https://orcid.org/0000-0002-5773-967X
Mahyar Rajabi-KochiChemical Engineering & Applied Chemistry, University of Toronto Toronto Ontario M5S 3E5 Canada.ORCID https://orcid.org/0009-0000-6392-3994
Kadi L SaarYusuf Hamied Department of Chemistry, University of Cambridge Cambridge CB2 1EW UK.ORCID https://orcid.org/0000-0002-5926-3628
Fahimeh Hooriabad SaboorChemical Engineering Department, University of Mohaghegh Ardabili P. O. Box 179 Ardabil Iran.ORCID https://orcid.org/0000-0001-7729-0673
Morteza SagharichihaDepartment of Chemical Engineering, College of Engineering, University of Tehran Tehran Iran.
K J SchmidtDepartment of Computer Science, University of Chicago Chicago IL 60637 USA.ORCID https://orcid.org/0000-0002-9373-0058
Jiale ShiDepartment of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA.ORCID https://orcid.org/0000-0002-5447-3925
Elena SimoneDepartment of Applied Science and Technology (DISAT), Politecnico di Torino 10129 Turino Italy.ORCID https://orcid.org/0000-0003-4000-2222
Dennis SvatunekInstitute of Applied Synthetic Chemistry, TU Wien Getreidemarkt 9 1060 Vienna Austria.ORCID https://orcid.org/0000-0003-1101-2376
Marco TaddeiDipartimento di Chimica e Chimica Industriale, Unità di Ricerca INSTM, Università di Pisa Via Giuseppe Moruzzi 13 56124 Pisa Italy.ORCID https://orcid.org/0000-0003-2805-6375
Igor TetkoBIGCHEM GmbH Valerystraße 49 85716 Unterschleißheim Germany.ORCID https://orcid.org/0000-0002-6855-0012
Domonkos TolnaiInstitute of Metallic Biomaterials, Helmholtz Zentrum Hereon Geesthacht Germany.ORCID https://orcid.org/0000-0002-1139-4709
Sahar VahdatifarDepartment of Chemical Engineering, College of Engineering, University of Tehran Tehran Iran.ORCID https://orcid.org/0000-0002-5415-4086
Jonathan WhitmerDepartment of Chemical and Biomolecular Engineering, University of Notre Dame Notre Dame Indiana 46556 USA.ORCID https://orcid.org/0000-0003-0370-0873
D C Florian WielandInstitute of Metallic Biomaterials, Helmholtz Zentrum Hereon Geesthacht Germany.ORCID https://orcid.org/0000-0002-8594-8292
Regine Willumeit-RömerInstitute of Metallic Biomaterials, Helmholtz Zentrum Hereon Geesthacht Germany.ORCID https://orcid.org/0000-0002-6004-6946
Andreas ZüttelLaboratory of Materials for Renewable Energy (LMER), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland.ORCID https://orcid.org/0000-0002-5708-1855
Berend SmitLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL) Rue de l'Industrie 17 CH-1951 Sion Switzerland Berend.Smit@epfl.ch.ORCID https://orcid.org/0000-0003-4653-8562
Funding
No grant is acknowledged in the PubMed record.
Abstract
The current generation of large language models (LLMs) has limited chemical knowledge. Recently, it has been shown that these LLMs can learn and predict chemical properties through fine-tuning. Using natural language to train machine learning models opens doors to a wider chemical audience, as field-specific featurization techniques can be omitted. In this work, we explore the potential and limitations of this approach. We studied the performance of fine-tuning three open-source LLMs (GPT-J-6B, Llama-3.1-8B, and Mistral-7B) for a range of different chemical questions. We benchmark their performances against "traditional" machine learning models and find that, in most cases, the fine-tuning approach is superior for a simple classification problem. Depending on the size of the dataset and the type of questions, we also successfully address more sophisticated problems. The most important conclusions of this work are that, for all datasets considered, their conversion into an LLM fine-tuning training set is straightforward and that fine-tuning with even relatively small datasets leads to predictive models. These results suggest that the systematic use of LLMs to guide experiments and simulations will be a powerful technique in any research study, significantly reducing unnecessary experiments or computations.
Identifiers
What OpenQuestion holds
Textmetadata
LicenceCC BY
Read underepoch 390
Registered trials
None linked
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.